DETECTION OF SPURIOUS STATES OF NEURAL NETWORKS

被引：1

作者：

CRAMA, Y

HANSEN, P

JAUMARD, B

机构：

[1] ECOLE HAUT ETUD COMMERCIALES,MONTREAL H3T 1V6,QUEBEC,CANADA

[2] RUTGERS STATE UNIV,RUTCOR,NEW BRUNSWICK,NJ 08903

[3] ECOLE POLYTECH,GERAD,MONTREAL H3C 3A7,QUEBEC,CANADA

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 01期

关键词：

D O I：

10.1109/72.80307

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study the complexity and propose an algorithm for the problem of determining, given p vectors of {-1, 1}n, all linear combinations of them which are also in {-1, 1}n. Computational results are reported. This problem corresponds to the detection of spurious states in neural networks.

引用

页码：165 / 168

页数：4

共 5 条

[1] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

[2] ASSOCIATIVE RECALL OF MEMORY WITHOUT ERRORS [J].

KANTER, I ;

SOMPOLINSKY, H .

PHYSICAL REVIEW A, 1987, 35 (01) :380-392

[3]

Nemhauser G. L., 1988, INTEGER COMBINATORIA

[4] ON SUBSPACES SPANNED BY RANDOM SELECTIONS OF +/-1 VECTORS [J].

ODLYZKO, AM .

JOURNAL OF COMBINATORIAL THEORY SERIES A, 1988, 47 (01) :124-133

[5] COLLECTIVE COMPUTATIONAL PROPERTIES OF NEURAL NETWORKS - NEW LEARNING-MECHANISMS [J].

PERSONNAZ, L ;

GUYON, I ;

DREYFUS, G .

PHYSICAL REVIEW A, 1986, 34 (05) :4217-4228

← 1 →